CN109847916A - A kind of energy conservation optimizing method of cement raw material vertical mill system - Google Patents
A kind of energy conservation optimizing method of cement raw material vertical mill system Download PDFInfo
- Publication number
- CN109847916A CN109847916A CN201811604430.9A CN201811604430A CN109847916A CN 109847916 A CN109847916 A CN 109847916A CN 201811604430 A CN201811604430 A CN 201811604430A CN 109847916 A CN109847916 A CN 109847916A
- Authority
- CN
- China
- Prior art keywords
- variable
- data
- optimal
- coding
- feeding capacity
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 26
- 239000004568 cement Substances 0.000 title claims abstract description 18
- 239000002994 raw material Substances 0.000 title claims abstract description 17
- 238000004134 energy conservation Methods 0.000 title claims abstract description 15
- 238000000227 grinding Methods 0.000 claims abstract description 35
- 230000008676 import Effects 0.000 claims abstract description 5
- 238000010801 machine learning Methods 0.000 claims abstract description 5
- 238000012216 screening Methods 0.000 claims description 20
- 238000009826 distribution Methods 0.000 claims description 18
- 230000003044 adaptive effect Effects 0.000 claims description 17
- 238000005457 optimization Methods 0.000 claims description 6
- 230000002159 abnormal effect Effects 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 5
- 230000006870 function Effects 0.000 claims description 5
- 230000015572 biosynthetic process Effects 0.000 claims description 4
- 238000003860 storage Methods 0.000 claims description 4
- 230000010354 integration Effects 0.000 claims description 3
- 239000004744 fabric Substances 0.000 claims 1
- 238000004519 manufacturing process Methods 0.000 abstract description 11
- 238000005192 partition Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 241001269238 Data Species 0.000 description 2
- 238000005265 energy consumption Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000012913 prioritisation Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 239000000843 powder Substances 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B02—CRUSHING, PULVERISING, OR DISINTEGRATING; PREPARATORY TREATMENT OF GRAIN FOR MILLING
- B02C—CRUSHING, PULVERISING, OR DISINTEGRATING IN GENERAL; MILLING GRAIN
- B02C23/00—Auxiliary methods or auxiliary devices or accessories specially adapted for crushing or disintegrating not provided for in preceding groups or not specially adapted to apparatus covered by a single preceding group
- B02C23/02—Feeding devices
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B02—CRUSHING, PULVERISING, OR DISINTEGRATING; PREPARATORY TREATMENT OF GRAIN FOR MILLING
- B02C—CRUSHING, PULVERISING, OR DISINTEGRATING IN GENERAL; MILLING GRAIN
- B02C25/00—Control arrangements specially adapted for crushing or disintegrating
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
Landscapes
- Engineering & Computer Science (AREA)
- Food Science & Technology (AREA)
- General Engineering & Computer Science (AREA)
- Manufacturing & Machinery (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Feedback Control In General (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of energy conservation optimizing methods of cement raw material vertical mill system, under the premise of not changing any structure of production equipment and principle, not increasing additional measuring point, do not affect the normal production, by the method for machine learning, intelligentized offer safely, conveniently, reasonable aid decision.This method comprises: acquisition historical operating data, form multiple historical operation models, historical operating data includes controlled variable, and controlled variable includes grinding machine grinding pressure, grinding machine import negative pressure, grinding machine outlet negative pressure, Hot-blast valve aperture, cold wind valve opening, mill entrance temperature, grinding machine outlet temperature, blower valve opening；Divide feeding capacity subregion；According to the height of single machine electrisity consumption, the historical operation of the same feeding capacity subregion is ranked up, obtains the optimal historical operation record of a feeding capacity subregion, the optimal historical operation record of all feeding capacity subregions is merged, optimal recommendation tables are formed；The Optimum Operation suggestion of equipment is obtained according to real-time working condition and optimal recommendation tables.
Description
Technical field
The present invention relates to energy conservation field more particularly to a kind of energy saving optimizing sides of cement raw material vertical mill system
Method.
Background technique
Energy saving optimizing under cement raw material vertical mill system production qualification and constant rate of production is the important topic of cement plant concern.
Its difficult point one is that real-time feeding capacity fluctuation is big, and worker needs manually to be finely tuned in real time, according to conventional management
And mode of operation, it can only accomplish that yield is normal, can not accomplish the optimal of energy consumption；
Its difficult point two needs worker according to expert advice, i.e., according to the general operation setting Value Operations artificially provided, no
Same expert, the operation setting value provided is different, can not equally accomplish energy-saving.
It is therefore desirable to propose a kind of adaptive low cost, safely and conveniently intelligent assistant decision scheme, water is helped
Mud factory provides a more accurately and reliably Optimizing Suggestions, to reach intelligent operation, and energy saving or even excellent under constant rate of production
The effect of production.
Summary of the invention
The present invention in order to solve the above technical problems, provide a kind of energy conservation optimizing method of cement raw material vertical mill system,
Under the premise of not changing any structure of production equipment and principle, not increasing additional measuring point, do not affect the normal production, pass through engineering
The method of habit, intelligentized offer safely, conveniently, reasonable aid decision.
The described method includes: acquisition historical operating data, forms multiple historical operation models, the historical operating data packet
Controlled variable is included, the controlled variable includes grinding machine grinding pressure, grinding machine import negative pressure, grinding machine exports negative pressure, Hot-blast valve is opened
Degree, cold wind valve opening, mill entrance temperature, grinding machine outlet temperature, blower valve opening；
Feeding capacity subregion is marked off according to the feeding capacity of grinding machine；
According to the height of single machine electrisity consumption, the historical operation of the same feeding capacity subregion is ranked up, one is obtained and feeds
The optimal historical operation record of doses subregion merges the optimal historical operation record of all feeding capacity subregions, forms optimal push away
Recommend table；
Further, the Optimum Operation suggestion of equipment is obtained according to real-time working condition and the optimal recommendation tables.
Further, before obtaining optimal historical operation record, to the historical operation number by way of machine learning
According to box traction substation distribution statistics are carried out, upper and lower bound is obtained, rejects the abnormal data except upper and lower bound.
Further, after rejecting the abnormal data in historical operating data, pass through the normal distribution feelings of autonomous learning data
Condition, adaptive to determine different data screening rule, specific logic is as follows:
If VMIN<μ -3 σ and VMAX>+3 σ of μ, take (+3 σ of μ -3 σ, μ) range as data screening rule；
If VMIN > μ -3 σ and+3 σ of VMAX > μ, take (+3 σ of VMIN, μ) range as data screening rule；
If VMIN < μ -3 σ and+3 σ of VMAX < μ, take (μ -3 σ, VMAX) range as data screening rule；
If VMIN>μ -3 σ and+3 σ of VMAX<μ, take (VMIN, VMAX) range as data screening rule；
Wherein, VMIN is variable minimum value, VMAX variable maximum, μ mean variable value, σ variable standard deviation.
Further, rejecting abnormalities data and after determining different data screening rule according to the normal distribution situation of data,
Sliding-model control is carried out to historical operating data, then adaptive high-quality coding is carried out to historical operation model.
After coding, the frequency that each coding occurs in the same feeding capacity subregion is counted, and descending row is carried out according to frequency
Sequence；It counts identical and encodes corresponding single machine power consumption, identical coding is subjected to integration duplicate removal, formation encodes alone, and encodes alone
Corresponding single machine power consumption is equal to the mean value of the single machine power consumption of all identical codings, obtains top ten in descending sort and encodes alone pair
The single machine power consumption answered, the optimal historical operation record for selecting single machine power consumption minimum as place feeding capacity subregion, obtains simultaneously
Corresponding optimal recommendation tables.
Wherein, the coding is corresponded with the historical operation model, and coding is mapping of each variable to model, can
To model orientation, i.e., corresponding model can be quickly found out according to variable, by coding mode, sample can not only be substantially reduced
Memory headroom improves model training speed, and can greatly improve study accuracy.
Coding represents grinding machine grinding pressure, grinding machine import negative pressure, grinding machine outlet negative pressure, Hot-blast valve aperture, cold blast sliding valve
The variables such as door aperture, mill entrance temperature, grinding machine outlet temperature, blower valve opening, different variables are according to data area.
Specific coding calculation formula are as follows: coding=bracket function ((variable-variable minimum)/variable step-length),
The application will not admix any subjective warp using adaptive high-quality coding, variable minimum and variable step-length
It tests, data itself is depended on, departing from artificial fixation subjective experience.
Wherein, the variable minimum depends on just too distribution situation:
If standardized normal distribution data, then variable minimum=mean value -3* standard deviation；
Left avertence state if (coefficient of skew SK < -0.1) distributed data (having long-tail on the left of distribution), when (kurtosis in data set
COEFFICIENT K T>0), then variable minimum=mean value -3* standard deviation, when data disperse (coefficient of kurtosis KT<0), then variable minimum
=mean value-standard deviation；
Right avertence state if (coefficient of skew SK > 0.1) distributed data (having long-tail on the right side of distribution), when (kurtosis in data set
COEFFICIENT K T>0), then variable minimum=mean value -3* standard deviation, when data disperse (coefficient of kurtosis KT<0), then variable minimum
=mean value-standard deviation；
The variable step-length depends on data precision variable quantity:
DIFF=(mean value+3* standard deviation)-(mean value -3* standard deviation)
IF DIFF≤5AND DIFF >=0.5:
Variable step-length=0.1；
DIFF≤50 ELIF DIFF > 5AND:
Variable step-length=1；
DIFF < 0.5 ELIF:
Variable step-length=0.01；
DIFF > 50 ELIF:
Variable step-length=10.
Further, when carrying out Optimum Operation suggestion according to optimal recommendation tables, to the optimal historical operation record of recommendation
Coding is decoded, and decoding calculation formula is as follows:
Variance=variance encodes * variable step-length+variable minimum.
Further, according to real-time working condition, the Optimum Operation suggestion of the corresponding operating condition of optimal recommendation tables is iterated excellent
Change, specific iterative optimization procedure is the operation model formation real-time coding for operating generation, and real-time coding is encoded alone with described
Matching is judged as preferably when matching distance is zero and the single machine power consumption of real-time coding is lower than the single machine power consumption encoded alone
Operation note stores the operation note, and recalculates single machine power consumption mean value, that is, obtains the new single machine electricity encoded alone
Consumption, then with place feeding capacity subregion it is other encode alone compared with appearance frequency and single machine power consumption, thus feeding where updating
Measure the optimal historical operation record of subregion；When the coding alone that matching is zero less than distance, the real-time coding is classified as newly
Coding alone, then with place feeding capacity subregion it is other alone encode compared with appearance frequency and single machine power consumption, to update
The optimal historical operation record of place feeding capacity subregion.
By the above-mentioned description of this invention it is found that compared to the prior art, the present invention has the advantage that
1, by log history operation note, the Optimum Operation of equipment is obtained according to real-time working condition and the optimal recommendation tables
It is recommended that reaching energy-saving；
2, using adaptive screening rule and adaptive high-quality coding, departing from artificial fixation subjective experience, no
It admixes any subjective opinion or observes the experience after data statistics, first adaptive learning adjusts screening rule, and it is normal to extract safety
Worth of data, then by adaptive learning adjust coding parameters of formula, potential valence is excavated in historical data to reach
Value, the prioritization scheme recommended are objective, reasonable, reliable, safe；
3, online pushing speed of the invention is fast, only need to judge which feeding capacity subregion belonged to, can be from storage most
The corresponding recommended suggestion of extraction in excellent recommendation tables rapidly and efficiently, possesses fast efficiency advisory speed, much meets every 3s mono-
The demand of recommended suggestion；
4, the present invention possesses Fast Learning efficiency, includes online updating function.In the optimal recommendation tables of iteration, it is not necessarily to needle
All feeding capacity partition datas are learnt again, remove the Optimum Operation record for obtaining each feeding capacity subregion, it only need to be according to feeding
Amount judges corresponding feeding capacity subregion, then is learnt again to corresponding partition data, then only need to be by this point in optimal recommendation tables
The optimal historical operation record in area is updated.
Detailed description of the invention
The drawings described herein are used to provide a further understanding of the present invention, constitutes a part of the invention, this hair
Bright illustrative embodiments and their description are used to explain the present invention, and are not constituted improper limitations of the present invention.
Wherein:
Fig. 1 is a kind of flow diagram of the energy conservation optimizing method embodiment one of cement raw material vertical mill system of the present invention；
Specific embodiment
In order to be clearer and more clear technical problems, technical solutions and advantages to be solved, tie below
Drawings and examples are closed, the present invention will be described in further detail.It should be appreciated that specific embodiment described herein is only used
To explain the present invention, it is not intended to limit the present invention.
Embodiment one: a kind of energy conservation optimizing method of cement raw material vertical mill system is not changing any structure of production equipment
With principle, do not increase additional measuring point, do not affect the normal production under the premise of, by the method for machine learning, intelligentized offer
Safely, conveniently, reasonable aid decision.
The described method includes: acquisition historical operating data, forms multiple historical operation models, the historical operating data packet
Include controlled variable, rule-based filtering variable and the lesser variable of correlation, the controlled variable include grinding machine grinding pressure, grinding machine into
Mouth negative pressure, grinding machine export negative pressure, Hot-blast valve aperture, cold wind valve opening, mill entrance temperature, grinding machine outlet temperature, blower
Valve opening, the rule-based filtering variable include grinding machine vibration values and powder concentrator electric current, and the present embodiment only considers how optimization phase
It closes and controlled variable is as energy-saving Optimizing Suggestions, to realize under the premise of not affecting the normal production, reduce mill
Machine and circulating fan energy consumption.
Feeding capacity subregion is marked off according to the feeding capacity of grinding machine.
According to the height of single machine electrisity consumption, the historical operation of the same feeding capacity subregion is ranked up, one is obtained and feeds
The optimal historical operation record of doses subregion merges the optimal historical operation record of all feeding capacity subregions, forms optimal push away
Recommend table.
The Optimum Operation suggestion of equipment is obtained according to real-time working condition and the optimal recommendation tables.
Embodiment two: on the basis of example 1, being analyzed and processed historical operating data, specific: to obtain
Before optimal historical operation record, box traction substation distribution statistics are carried out to the historical operating data by way of machine learning, are obtained
To upper and lower bound, rejects the abnormal data except upper and lower bound and pass through the normal distribution feelings of autonomous learning data later
Condition, adaptive to determine different data screening rule, specific logic is as follows:
If VMIN<μ -3 σ and VMAX>+3 σ of μ, take (+3 σ of μ -3 σ, μ) range as data screening rule；
If VMIN > μ -3 σ and+3 σ of VMAX > μ, take (+3 σ of VMIN, μ) range as data screening rule；
If VMIN < μ -3 σ and+3 σ of VMAX < μ, take (μ -3 σ, VMAX) range as data screening rule；
If VMIN>μ -3 σ and+3 σ of VMAX<μ, take (VMIN, VMAX) range as data screening rule；
Wherein, VMIN is variable minimum value, VMAX variable maximum, μ mean variable value, σ variable standard deviation, and initial target
It is as follows that the hardness of grinding machine host electric current and circulating fan high-tension current meets condition:
Grinding machine host electric current: [90,125]
Circulating fan high-tension current: [60,70].
Then sliding-model control is carried out to historical operating data, then adaptive high-quality coding is carried out to historical operation model,
Such as: X11, X12, X13 ..., X1N see Fig. 1.
After coding, the frequency that each coding occurs in the same feeding capacity subregion is counted, and descending row is carried out according to frequency
Sequence；It counts identical and encodes corresponding single machine power consumption Y1, identical coding is subjected to integration duplicate removal, formation encodes alone, and compiles alone
The corresponding single machine power consumption Y2 of code is equal to the mean value of the single machine power consumption Y1 of all identical codings, obtains in descending sort top ten alone
Corresponding single machine power consumption Y12 is encoded, the optimal historical operation for selecting single machine power consumption Ybest minimum as place feeding capacity subregion
Record, while obtaining corresponding optimal recommendation tables.
Wherein, the coding is corresponded with the historical operation model, and coding is mapping of each variable to model, can
To model orientation, i.e., corresponding model can be quickly found out according to variable, by coding mode, sample can not only be substantially reduced
Memory headroom improves model training speed, and can greatly improve study accuracy.
Coding represents grinding machine grinding pressure, grinding machine import negative pressure, grinding machine outlet negative pressure, Hot-blast valve aperture, cold blast sliding valve
The variables such as door aperture, mill entrance temperature, grinding machine outlet temperature, blower valve opening, different variables are according to data area.
Specific coding calculation formula are as follows: coding=bracket function ((variable-variable minimum)/variable step-length),
The application will not admix any subjective warp using adaptive high-quality coding, variable minimum and variable step-length
It tests, data itself is depended on, departing from artificial fixation subjective experience.
Wherein, the variable minimum depends on just too distribution situation:
If standardized normal distribution data, then variable minimum=mean value -3* standard deviation；
Left avertence state if (coefficient of skew SK < -0.1) distributed data (having long-tail on the left of distribution), when (kurtosis in data set
COEFFICIENT K T>0), then variable minimum=mean value -3* standard deviation, when data disperse (coefficient of kurtosis KT<0), then variable minimum
=mean value-standard deviation；
Right avertence state if (coefficient of skew SK > 0.1) distributed data (having long-tail on the right side of distribution), when (kurtosis in data set
COEFFICIENT K T>0), then variable minimum=mean value -3* standard deviation, when data disperse (coefficient of kurtosis KT<0), then variable minimum
=mean value-standard deviation；
The variable step-length depends on data precision variable quantity:
DIFF=(mean value+3* standard deviation)-(mean value -3* standard deviation)
IF DIFF≤5AND DIFF >=0.5:
Variable step-length=0.1；
DIFF≤50 ELIF DIFF > 5AND:
Variable step-length=1；
DIFF < 0.5 ELIF:
Variable step-length=0.01；
DIFF > 50 ELIF:
Variable step-length=10.
When carrying out Optimum Operation suggestion according to optimal recommendation tables, the coding of the optimal historical operation record of recommendation is solved
Code, decoding calculation formula are as follows:
Variance=variance encodes * variable step-length+variable minimum.
Embodiment three, on the basis of example 2, according to real-time working condition, to the optimal of the corresponding operating condition of optimal recommendation tables
Suggestion for operation is iterated optimization, specific iterative optimization procedure are as follows:
The operation model that operation generates forms real-time coding, by real-time coding and the codes match alone, when match away from
When from being lower than the single machine power consumption encoded alone for the single machine power consumption of zero and real-time coding, it is judged as preferably operation note, by this
Operation note storage, and recalculate single machine power consumption mean value, that is, the new single machine power consumption encoded alone is obtained, then feed with place
Other codings alone of doses subregion compare the frequency and single machine power consumption of appearance, so that the optimal of feeding capacity subregion where updating is gone through
History operation note；
When the coding alone that matching is zero less than distance, the real-time coding is classified as to new coding alone, then with institute
Compare the frequency and single machine power consumption of appearance in other codings alone of feeding capacity subregion, so that feeding capacity subregion where updating is most
Excellent historical operation record.
In conclusion compared to the prior art, a kind of energy saving optimizing side for cement raw material vertical mill system that the application proposes
Method has the advantage that
1, by log history operation note, the Optimum Operation of equipment is obtained according to real-time working condition and the optimal recommendation tables
It is recommended that reaching energy-saving；
2, using adaptive screening rule and adaptive high-quality coding, departing from artificial fixation subjective experience, no
It admixes any subjective opinion or observes the experience after data statistics, first adaptive learning adjusts screening rule, and it is normal to extract safety
Worth of data, then by adaptive learning adjust coding parameters of formula, potential valence is excavated in historical data to reach
Value, the prioritization scheme recommended are objective, reasonable, reliable, safe；
3, online pushing speed of the invention is fast, only need to judge which feeding capacity subregion belonged to, can be from storage most
The corresponding recommended suggestion of extraction in excellent recommendation tables rapidly and efficiently, possesses fast efficiency and advisory speed, much meets every 3s mono-
The demand of a recommended suggestion；
4, the present invention possesses Fast Learning efficiency, includes online updating function.In the optimal recommendation tables of iteration, it is not necessarily to needle
All feeding capacity partition datas are learnt again, remove the Optimum Operation record for obtaining each feeding capacity subregion, it only need to be according to feeding
Amount judges corresponding feeding capacity subregion, then is learnt again to corresponding partition data, then only need to be by this point in optimal recommendation tables
The optimal historical operation record in area is updated.
The present invention is exemplarily described above in conjunction with attached drawing, it is clear that the present invention implements not by aforesaid way
Limitation, as long as the improvement for the various unsubstantialities that the inventive concept and technical scheme of the present invention carry out is used, or without changing
It is within the scope of the present invention into the conception and technical scheme of the invention are directly applied to other occasions.
Claims (8)
1. a kind of energy conservation optimizing method of cement raw material vertical mill system, which is characterized in that
Acquire historical operating data, form multiple historical operation models, the historical operating data includes controlled variable, it is described can
Control variable includes grinding machine grinding pressure, grinding machine import negative pressure, grinding machine outlet negative pressure, Hot-blast valve aperture, cold wind valve opening, mill
Machine inlet temperature, grinding machine outlet temperature, blower valve opening；
Feeding capacity subregion is obtained according to feeding capacity；
According to the height of single machine electrisity consumption, the historical operation of the same feeding capacity subregion is ranked up, obtains a feeding capacity
The optimal historical operation record of all feeding capacity subregions is merged, forms optimal recommendation tables by the optimal historical operation record of subregion.
2. a kind of energy conservation optimizing method of cement raw material vertical mill system according to claim 1, which is characterized in that according to reality
When operating condition and the optimal recommendation tables obtain the Optimum Operation suggestion of equipment.
3. a kind of energy conservation optimizing method of cement raw material vertical mill system according to claim 1, which is characterized in that obtaining
Before optimal historical operation record, box traction substation distribution statistics are carried out to the historical operating data by way of machine learning, are obtained
To upper and lower bound, the abnormal data except upper and lower bound is rejected.
4. a kind of energy conservation optimizing method of cement raw material vertical mill system according to claim 3, which is characterized in that rejecting is gone through
It is adaptive to determine different data screening rule after abnormal data in history operation data, pass through the normal state point of autonomous learning data
Cloth situation, specific logic are as follows:
If VMIN<μ -3 σ and VMAX>+3 σ of μ, take (+3 σ of μ -3 σ, μ) range as data screening rule；
If VMIN > μ -3 σ and+3 σ of VMAX > μ, take (+3 σ of VMIN, μ) range as data screening rule；
If VMIN < μ -3 σ and+3 σ of VMAX < μ, take (μ -3 σ, VMAX) range as data screening rule；
If VMIN>μ -3 σ and+3 σ of VMAX<μ, take (VMIN, VMAX) range as data screening rule；
Wherein, VMIN is variable minimum value, VMAX variable maximum, μ mean variable value, σ variable standard deviation.
5. a kind of energy conservation optimizing method of cement raw material vertical mill system according to claim 4, which is characterized in that history
Operation data carries out sliding-model control and carries out adaptive high-quality coding to historical operation model；Count the same feeding capacity subregion
In it is each coding occur frequency, and according to frequency carry out descending sort；It counts identical and encodes corresponding single machine power consumption, it will be identical
Coding carries out integration duplicate removal, and formation encodes alone, and encodes the single machine that corresponding single machine power consumption is equal to all identical codings alone
The mean value of power consumption, obtain descending sort in top ten encode corresponding single machine power consumption alone, select single machine power consumption minimum as
The optimal historical operation record of place feeding capacity subregion, while obtaining corresponding optimal recommendation tables.
6. a kind of energy conservation optimizing method of cement raw material vertical mill system according to claim 5, which is characterized in that the volume
Code is corresponded with the historical operation model, specific coding calculation formula are as follows: ((variable-variable is minimum for coding=bracket function
Value)/variable step-length),
The variable minimum depends on just too distribution situation:
If standardized normal distribution data, then variable minimum=mean value -3* standard deviation；
Left avertence state if (coefficient of skew SK < -0.1) distributed data (having long-tail on the left of distribution), when (coefficient of kurtosis in data set
KT>0), then variable minimum=mean value -3* standard deviation, when data disperse (coefficient of kurtosis KT<0), then variable minimum=
Value-standard deviation；
Right avertence state if (coefficient of skew SK > 0.1) distributed data (having long-tail on the right side of distribution), when (coefficient of kurtosis in data set
KT>0), then variable minimum=mean value -3* standard deviation, when data disperse (coefficient of kurtosis KT<0), then variable minimum=
Value-standard deviation；
The variable step-length depends on data precision variable quantity:
DIFF=(mean value+3* standard deviation)-(mean value -3* standard deviation)
IF DIFF≤5AND DIFF >=0.5:
Variable step-length=0.1；
DIFF≤50 ELIF DIFF > 5AND:
Variable step-length=1；
DIFF < 0.5 ELIF:
Variable step-length=0.01；
DIFF > 50 ELIF:
Variable step-length=10.
7. a kind of energy conservation optimizing method of cement raw material vertical mill system according to claim 5, which is characterized in that according to most
When excellent recommendation tables carry out Optimum Operation suggestion, the coding of the optimal historical operation record of recommendation is decoded, decoding calculates public
Formula is as follows: variance=variance encodes * variable step-length+variable minimum.
8. a kind of energy conservation optimizing method of cement raw material vertical mill system according to claim 5, which is characterized in that according to reality
When operating condition, optimization is iterated to the Optimum Operation suggestion of the corresponding operating condition of optimal recommendation tables, specific iterative optimization procedure is, grasps
Make the operation model generated and form real-time coding, by real-time coding and the codes match alone, when matching distance is zero and reality
When the single machine power consumption that encodes when being lower than the single machine power consumption encoded alone, be judged as preferably operation note, which deposited
Storage, and recalculates single machine power consumption mean value, that is, obtains the new single machine power consumption encoded alone, then with place feeding capacity subregion
Other codings alone compare the frequency and single machine power consumption of appearance, thus the optimal historical operation note of feeding capacity subregion where updating
Record；When the coding alone that matching is zero less than distance, the real-time coding is classified as to new coding alone, then with place feeding
Other codings alone of amount subregion compare the frequency and single machine power consumption of appearance, thus the optimal history of feeding capacity subregion where updating
Operation note.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811604430.9A CN109847916B (en) | 2018-12-26 | 2018-12-26 | Energy-saving optimization method of cement raw material vertical mill system |
| PCT/CN2019/120980 WO2020134801A1 (en) | 2018-12-26 | 2019-11-26 | Energy-saving optimization method of cement raw material vertical mill system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811604430.9A CN109847916B (en) | 2018-12-26 | 2018-12-26 | Energy-saving optimization method of cement raw material vertical mill system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109847916A true CN109847916A (en) | 2019-06-07 |
| CN109847916B CN109847916B (en) | 2021-01-12 |
Family
ID=66892607
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811604430.9A Active CN109847916B (en) | 2018-12-26 | 2018-12-26 | Energy-saving optimization method of cement raw material vertical mill system |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN109847916B (en) |
| WO (1) | WO2020134801A1 (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110471375A (en) * | 2019-07-08 | 2019-11-19 | 杭州电子科技大学 | A kind of anti-interference optimization tracking of cement denitrification process |
| WO2020134801A1 (en) * | 2018-12-26 | 2020-07-02 | 厦门邑通软件科技有限公司 | Energy-saving optimization method of cement raw material vertical mill system |
| CN112506134A (en) * | 2019-09-16 | 2021-03-16 | 阿里巴巴集团控股有限公司 | Method, device and equipment for determining control variable value |
| WO2021225544A1 (en) * | 2020-05-04 | 2021-11-11 | Sabanci Di̇ji̇tal Teknoloji̇ Hi̇zmetleri̇ A.Ş. | System and method for ai controlling mill operations to lower electricity consumption |
| CN116474928A (en) * | 2023-06-25 | 2023-07-25 | 中才邦业(杭州)智能技术有限公司 | Cement mill energy consumption optimization method and system |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112949183B (en) * | 2021-03-04 | 2024-01-16 | 上海交通大学宁波人工智能研究院 | Abnormal working condition detection system and method for cement raw material vertical mill system |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4833617A (en) * | 1987-08-14 | 1989-05-23 | General Electric Company | Solid modeling based adaptive feedrate control for NC machining |
| US20050086202A1 (en) * | 2003-10-20 | 2005-04-21 | Cheng George S. | Model-free adaptive (MFA) optimization |
| US20060060684A1 (en) * | 2004-08-13 | 2006-03-23 | Invensys Systems, Inc. | Methods and systems for cement finishing mill control |
| CN1836785A (en) * | 2006-04-24 | 2006-09-27 | 西安交通大学 | Powder-making system automatic control method for heat engine plant steel ball coal grinding mill |
| CN101318158A (en) * | 2008-03-17 | 2008-12-10 | 西安艾贝尔科技发展有限公司 | Control method for grinding process optimization of cement factory |
| CN102402186A (en) * | 2011-12-20 | 2012-04-04 | 西安艾贝尔科技发展有限公司 | Optimized control method for milling process in cement plant |
| CN103028480A (en) * | 2012-12-10 | 2013-04-10 | 上海凯盛节能工程技术有限公司 | Intelligent control system for vertical mill based on fuzzy PID (proportion integration differentiation) algorithm |
| CN106179633A (en) * | 2016-07-28 | 2016-12-07 | 洛阳矿山机械工程设计研究院有限责任公司 | A kind of method of adjustment of grinding machine intelligence automatic speed regulation system |
| CN106676934A (en) * | 2016-12-28 | 2017-05-17 | 东北大学 | Economical and optimal running control method and system for high-concentration grinding system |
| CN106990763A (en) * | 2017-04-20 | 2017-07-28 | 浙江大学 | A kind of Vertical Mill operation regulator control system and method based on data mining |
| CN107344138A (en) * | 2016-05-05 | 2017-11-14 | 中冶长天国际工程有限责任公司 | A kind of ore mill control method and device |
| CN108224393A (en) * | 2018-01-08 | 2018-06-29 | 中国恩菲工程技术有限公司 | Intelligent waste heat boiler optimal control method |
| CN108268597A (en) * | 2017-12-18 | 2018-07-10 | 中国电子科技集团公司第二十八研究所 | A kind of moving-target activity probability map construction and behavior intension recognizing method |
| CN108600756A (en) * | 2018-05-04 | 2018-09-28 | 上海大学 | Coding parameter self-adapting regulation method based on Monte Carlo method Markov chain |
| CN110302888A (en) * | 2019-07-15 | 2019-10-08 | 湖北白兆山水泥有限公司 | Cement mill Optimization of Energy Saving system |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100594066C (en) * | 2008-04-25 | 2010-03-17 | 东南大学 | Operation optimizing and energy-saving control method for intermediate storage iron shot mill flour milling system |
| CN102566551B (en) * | 2012-02-03 | 2014-07-09 | 北京华电天仁电力控制技术有限公司 | Data mining-based method for analyzing thermal power plant operation index optimal target value |
| WO2014185810A1 (en) * | 2013-05-13 | 2014-11-20 | Siemens Aktiengesellschaft | Method for adjusting final steel properties at steel mill facility |
| CN107016176A (en) * | 2017-03-24 | 2017-08-04 | 杭州电子科技大学 | A kind of hybrid intelligent overall boiler burning optimization method |
| CN107239066B (en) * | 2017-06-09 | 2018-02-16 | 浙江大学 | A kind of Vertical Mill operation closed-loop control device and method based on data mining |
| CN107818409A (en) * | 2017-10-23 | 2018-03-20 | 燕山大学 | The optimization method of manufacture of cement parameter and regulation section based on fuzzy association rules |
| CN109847916B (en) * | 2018-12-26 | 2021-01-12 | 厦门邑通软件科技有限公司 | Energy-saving optimization method of cement raw material vertical mill system |
-
2018
- 2018-12-26 CN CN201811604430.9A patent/CN109847916B/en active Active
-
2019
- 2019-11-26 WO PCT/CN2019/120980 patent/WO2020134801A1/en active Application Filing
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4833617A (en) * | 1987-08-14 | 1989-05-23 | General Electric Company | Solid modeling based adaptive feedrate control for NC machining |
| US20050086202A1 (en) * | 2003-10-20 | 2005-04-21 | Cheng George S. | Model-free adaptive (MFA) optimization |
| US20060060684A1 (en) * | 2004-08-13 | 2006-03-23 | Invensys Systems, Inc. | Methods and systems for cement finishing mill control |
| CN1836785A (en) * | 2006-04-24 | 2006-09-27 | 西安交通大学 | Powder-making system automatic control method for heat engine plant steel ball coal grinding mill |
| CN101318158A (en) * | 2008-03-17 | 2008-12-10 | 西安艾贝尔科技发展有限公司 | Control method for grinding process optimization of cement factory |
| CN102402186A (en) * | 2011-12-20 | 2012-04-04 | 西安艾贝尔科技发展有限公司 | Optimized control method for milling process in cement plant |
| CN103028480A (en) * | 2012-12-10 | 2013-04-10 | 上海凯盛节能工程技术有限公司 | Intelligent control system for vertical mill based on fuzzy PID (proportion integration differentiation) algorithm |
| CN107344138A (en) * | 2016-05-05 | 2017-11-14 | 中冶长天国际工程有限责任公司 | A kind of ore mill control method and device |
| CN106179633A (en) * | 2016-07-28 | 2016-12-07 | 洛阳矿山机械工程设计研究院有限责任公司 | A kind of method of adjustment of grinding machine intelligence automatic speed regulation system |
| CN106676934A (en) * | 2016-12-28 | 2017-05-17 | 东北大学 | Economical and optimal running control method and system for high-concentration grinding system |
| CN106990763A (en) * | 2017-04-20 | 2017-07-28 | 浙江大学 | A kind of Vertical Mill operation regulator control system and method based on data mining |
| CN108268597A (en) * | 2017-12-18 | 2018-07-10 | 中国电子科技集团公司第二十八研究所 | A kind of moving-target activity probability map construction and behavior intension recognizing method |
| CN108224393A (en) * | 2018-01-08 | 2018-06-29 | 中国恩菲工程技术有限公司 | Intelligent waste heat boiler optimal control method |
| CN108600756A (en) * | 2018-05-04 | 2018-09-28 | 上海大学 | Coding parameter self-adapting regulation method based on Monte Carlo method Markov chain |
| CN110302888A (en) * | 2019-07-15 | 2019-10-08 | 湖北白兆山水泥有限公司 | Cement mill Optimization of Energy Saving system |
Non-Patent Citations (1)
| Title |
|---|
| 杜文辽等: "大型立磨状态监测数据库管理系统研究与开发", 《机械设计与研究》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020134801A1 (en) * | 2018-12-26 | 2020-07-02 | 厦门邑通软件科技有限公司 | Energy-saving optimization method of cement raw material vertical mill system |
| CN110471375A (en) * | 2019-07-08 | 2019-11-19 | 杭州电子科技大学 | A kind of anti-interference optimization tracking of cement denitrification process |
| CN112506134A (en) * | 2019-09-16 | 2021-03-16 | 阿里巴巴集团控股有限公司 | Method, device and equipment for determining control variable value |
| CN112506134B (en) * | 2019-09-16 | 2024-08-20 | 阿里巴巴集团控股有限公司 | Method, device and equipment for determining control variable value |
| WO2021225544A1 (en) * | 2020-05-04 | 2021-11-11 | Sabanci Di̇ji̇tal Teknoloji̇ Hi̇zmetleri̇ A.Ş. | System and method for ai controlling mill operations to lower electricity consumption |
| CN116474928A (en) * | 2023-06-25 | 2023-07-25 | 中才邦业(杭州)智能技术有限公司 | Cement mill energy consumption optimization method and system |
| CN116474928B (en) * | 2023-06-25 | 2023-09-26 | 中才邦业(杭州)智能技术有限公司 | Cement mill energy consumption optimization method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109847916B (en) | 2021-01-12 |
| WO2020134801A1 (en) | 2020-07-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109847916A (en) | A kind of energy conservation optimizing method of cement raw material vertical mill system | |
| CN110302888A (en) | Cement mill Optimization of Energy Saving system | |
| CN108469180A (en) | The method for building up of sintering end point forecasting system based on big data and machine learning | |
| CN107038167A (en) | Big data excavating analysis system and its analysis method based on model evaluation | |
| CN110533092B (en) | Wind generating set SCADA data classification method based on operation condition and application | |
| CN103488561B (en) | A kind of kNN fault detection method of online upgrading master sample model | |
| CN101750964B (en) | Multivariable predictive control method with firing system based on pulse response die | |
| CN107578288A (en) | A kind of non-intrusion type load decomposition method for considering user power utilization pattern differentials | |
| CN106774243B (en) | PID performance estimating method | |
| CN110400018B (en) | Operation control method, system and device for coal-fired power plant pulverizing system | |
| CN105892287A (en) | Crop irrigation strategy based on fuzzy judgment and decision making system | |
| CN106371316B (en) | Water island dosing On-Line Control Method based on PSO LSSVM | |
| CN102930155A (en) | Method and device for acquiring early-warming parameters of power demands | |
| CN103217905A (en) | Facility agriculture greenhouse environment parameter self-adaptation controlling method | |
| CN115375009B (en) | Method for establishing intelligent monitoring linkage system for coagulation | |
| CN112530530A (en) | Method for calculating limestone slurry density optimal value algorithm model based on Matlab software | |
| CN103869783B (en) | A kind of concentrate yield on-line prediction method | |
| CN111612331A (en) | Fuzzy intelligent plant growth monitoring system based on soil water potential and control target threshold value obtaining method | |
| CN101598927B (en) | Control system of soda carbonization technique based on neural network and control method thereof | |
| CN117556196A (en) | Intelligent flocculant adding method and system for tap water plant | |
| CN117348558A (en) | Filter pressing production closed-loop modeling and optimizing control method based on big data analysis | |
| CN102676818B (en) | Prediction method for zinc powder effectiveness coefficient in wet zinc smelting and copper removal process | |
| CN108821435B (en) | Dissolved oxygen control method in sewage treatment | |
| CN103901855A (en) | kernel learning monitoring method for penicillin production process under unequal-length batch conditions | |
| CN115202190B (en) | Working condition dividing and identifying method for adjusting potential based on process index |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address |
Address after: 361000 one of unit 702, No. 1, xishanwei Road, phase III Software Park, Xiamen Torch High tech Zone, Xiamen, Fujian Province Patentee after: Xiamen Yitong Intelligent Technology Group Co.,Ltd. Address before: B11, 4th floor, 1036 Xiahe Road, Siming District, Xiamen City, Fujian Province, 361000 Patentee before: XIAMEN ETOM SOFTWARE TECHNOLOGY Co.,Ltd. |
|
| CP03 | Change of name, title or address | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: An energy-saving optimization method for a cement raw material vertical grinding system Effective date of registration: 20220816 Granted publication date: 20210112 Pledgee: Xiamen Branch of PICC Pledgor: Xiamen Yitong Intelligent Technology Group Co.,Ltd. Registration number: Y2022980012793 |
|
| PC01 | Cancellation of the registration of the contract for pledge of patent right | ||
| PC01 | Cancellation of the registration of the contract for pledge of patent right |
Granted publication date: 20210112 Pledgee: Xiamen Branch of PICC Pledgor: Xiamen Yitong Intelligent Technology Group Co.,Ltd. Registration number: Y2022980012793 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: Energy saving optimization method for a cement raw material vertical grinding system Granted publication date: 20210112 Pledgee: Agricultural Bank of China Limited Xiamen Lianqian Branch Pledgor: Xiamen Yitong Intelligent Technology Group Co.,Ltd. Registration number: Y2024980004722 |